Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    следующ

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _cond
    -0.07
     swelling
    -0.06
    円
    -0.06
     pap
    -0.06
     recur
    -0.06
    players
    -0.06
     Reed
    -0.06
    Lou
    -0.06
     tvoř
    -0.06
    자는
    -0.06
    POSITIVE LOGITS
     RJ
    0.07
    .jsx
    0.06
     olds
    0.06
     сосед
    0.06
    付き
    0.06
    .Singleton
    0.06
     fille
    0.06
    .Pre
    0.06
     vä
    0.06
     vyk
    0.06
    Act Density 0.011%

    No Known Activations